Data Visualizations and Analysis

ggplot(working_df, aes(x = log(pop_2018), y = massLoadFlowMGD)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  theme_bw() +
  labs(x = "Log of Population (2018)")

## `geom_smooth()` using formula 'y ~ x'

## Warning: Removed 17 rows containing non-finite values (stat_smooth).

## Warning: Removed 17 rows containing missing values (geom_point).

ggplot(working_df, aes(x = log(pop_2018),
                       y = parse_number(`TSS monthly average lbs/day`))) +
  geom_point() +
  theme_bw()

## Warning: 2 parsing failures.
## row col expected actual
##  13  -- a number     na
##  45  -- a number     na

## Warning: 2 parsing failures.
## row col expected actual
##  13  -- a number     na
##  45  -- a number     na

## Warning: Removed 19 rows containing missing values (geom_point).

working_df %>%
  filter(type1 %in% c("lagoons", "activated sludge")) %>%
  group_by(type1) %>%
  summarize(median = median(pop_2018, na.rm = TRUE))

## `summarise()` ungrouping output (override with `.groups` argument)

## # A tibble: 2 x 2
##   type1            median
##   <chr>             <dbl>
## 1 activated sludge  1962.
## 2 lagoons           1718.

library(viridis)

## Loading required package: viridisLite

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

p <- working_df %>%
  ggplot(aes(x = Region.x,
             fill = type1)) +
  geom_bar(position = "fill") +
  scale_fill_viridis_d(option = "C", na.value = "grey50") +
  scale_x_discrete(labels=c("Eastern", "Northwest", "West")) +
  theme_bw() +
  labs(x = "Region",
       fill = "Main Type",
       y = "Proportion",
       title = "Rural WWTPs in Oregon by Type")
p

ggplotly(p, tooltip = c("type1", "count"))

working_df %>%
  filter(type2 != c("na", NA)) %>%
  ggplot(aes(x = Region.x,
             fill = type2)) +
  geom_bar(position = "fill") +
  scale_fill_viridis_d(option = "C", na.value = "grey50") +
  scale_x_discrete(labels=c("Eastern", "Northwest", "West")) +
  theme_bw() +
  labs(x = "Region",
       fill = "Secondary Type",
       y = "Proportion",
       title = "Rural WWTPs in Oregon by Secondary Type")